Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/arcblock/agent-skills/media-uploadnpx skills add ArcBlock/agent-skills --skill media-uploadgit clone --depth 1 https://github.com/ArcBlock/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/arcblock/agent-skills/media-upload)<a href="https://agentmods.dev/skills/arcblock/agent-skills/media-upload"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/media-upload.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00126 | $0.02044 |
| Opus 5 | $0.00063 | $0.01022 |
| Sonnet 5 | $0.00025 | $0.00409 |
| Haiku 4.5 | $0.00013 | $0.00204 |
Grade A, and why
media-upload scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
media-upload — 媒体上传（图片/视频），输出 raw.githubusercontent.com URL
把媒体文件（截图、动图、录屏——单个或整目录）上传到公共图床仓（默认 ArcBlock/loop-agent-assets），
返回可匿名访问的 raw.githubusercontent.com/.../main/... URL。
Output language: 中文；代码 / 路径 / 命令保持原文。
⚠️ 上传统一，内嵌不统一（最容易踩的坑）
上传对 image/video 是同一套；但在 GitHub markdown 里怎么内嵌，按类型分流：
| 类型 | 扩展名 | 内嵌方式 |
|---|---|---|
| 图片 | png / jpg |  内联显示（#1334） |
| 动图 | gif |  内联播放（gif 是 image/gif，同图片路径） |
| 视频 | webm / mp4 / mov | 链接 [▶ 录屏](<raw-url>)，或尽力 <video src=...>；绝不 ——GitHub 不会把 raw 视频渲染成播放器，![]() 只会破图 |
判据只看扩展名：.png/.jpg/.gif → ![]()；.webm/.mp4/.mov → 链接。
机制 = 插件里两个通用脚本（任何仓库同样跑，自动从 git remote 探 source repo，落在 <slug>/<ctx>/）
先解析插件根，脚本都在其 scripts/ 下：
PLUGIN="${AGENTLOOP_ROOT:-$HOME/.claude/plugins/marketplaces/arcblock-agent-skills/plugins/agentloop}"
- 单个文件：
bash "$PLUGIN/scripts/gh-upload-media.sh" <media> [name]→ 自动选写通道（gh contents API / git push）→ content-type=image/*|video/*闸 → stdout 打印 raw.githubusercontent/main URL。 - 整目录：
SCREENSHOT_DIR=<dir> CONTEXT=<ctx> bash "$PLUGIN/scripts/gh-upload-dir.sh"→ 遍历目录（png/jpg/jpeg/gif/webm/mp4/mov）逐个调上面那个 → stdout 每行filename\turl；任一失败追加一行UPLOAD_FAILED\t<原因>（始终 exit 0，失败看这行不看退出码）。
Usage
/agentloop:media-upload <dir> # 上传目录下所有媒体 → filename\turl map
/agentloop:media-upload <file> # 单个（图片或视频）
# 消费方 skill 的 bash 里直接调脚本（自动化调机制、不调 slash 命令）：
SCREENSHOT_DIR="$SHOT_DIR" CONTEXT="pr${PR}" bash "$PLUGIN/scripts/gh-upload-dir.sh" > url-map.tsv
拿到 map 后按上表分流内嵌。收到 UPLOAD_FAILED 行时在报告顶部显示 > ⚠️ 媒体上传失败 — <原因>
并降级 SendUserFile 直投（不能内嵌，但不产出损坏文件）。
上传器两通道都不可用时：浏览器原生附件上传（第三层兜底，issue #3010）
SendUserFile 只把文件发给当前对话的人，不会让证据落地到 GitHub——PR/issue 上依旧没有可核验的
截图。这类 review 门控（ui-verify 的 UI 证据闸最典型）需要证据持久发布在 GitHub 上，gh 与图床
仓 clone 又都不可用时，唯一确定性可重复的兜底是驱动一个已登录 GitHub 的浏览器走原生附件上传
（本轮真实产出过 arc#2991 / arcblock-site#165 / Site PR #166 的截图证据）：
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 103 lines · 126 tokens per session scan A d838f5c43be7
media-upload is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 126 tokens to every session and 2,044 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…